Changes in the structure and/or the expression of protein coding genes were thought to be the major cause of cancer for many decades. The recent discovery of non-coding RNA (ncRNA) transcripts (i.e., microRNAs) suggests that the molecular biology of cancer is far more complex. MicroRNAs (miRNAs) have been under investigation due to their involvement in carcinogenesis, often taking up roles of tumor suppressors or oncogenes. Due to the slow nature of experimental identification of miRNA genes, computational procedures have been applied as a valuable complement to cloning. Numerous computational tools, implemented to recognize the features of miRNA biogenesis, have resulted in the prediction of novel miRNA genes. Computational approaches provide clues as to which are the dominant features that characterize these regulatory units and furthermore act by narrowing down the search space making experimental verification faster and cheaper. In combination with large scale, high throughput methods, such as deep sequencing, computational methods have aided in the discovery of putative molecular signatures of miRNA deregulation in human tumors. This review focuses on existing computational methods for identifying miRNA genes, provides an overview of the methodology undertaken by these tools, and underlies their contribution towards unraveling the role of miRNAs in cancer.