Macromolecules carrying biological information often consist of independent modules containing recurring structural motifs. Detection of a specific structural motif within a protein (or DNA) aids in elucidating the role played by the protein (DNA element) and the mechanism of its operation. The number of crystallographically known structures at high resolution is increasing very rapidly. Yet, comparison of three-dimensional structures is a laborious time-consuming procedure that typically requires a manual phase. To date, there is no fast automated procedure for structural comparisons. We present an efficient O(n3) worst case time complexity algorithm for achieving such a goal (where n is the number of atoms in the examined structure). The method is truly three-dimensional, sequence-order-independent, and thus insensitive to gaps, insertions, or deletions. This algorithm is based on the geometric hashing paradigm, which was originally developed for object recognition problems in computer vision. It introduces an indexing approach based on transformation invariant representations and is especially geared toward efficient recognition of partial structures in rigid objects belonging to large data bases. This algorithm is suitable for quick scanning of structural data bases and will detect a recurring structural motif that is a priori unknown. The algorithm uses protein (or DNA) structures, atomic labels, and their three-dimensional coordinates. Additional information pertaining to the structure speeds the comparisons. The algorithm is straightforwardly parallelizable, and several versions of it for computer vision applications have been implemented on the massively parallel connection machine. A prototype version of the algorithm has been implemented and applied to the detection of substructures in proteins.