The 21-gene recurrence score (RS) assay (Oncotype DX™) predicts the likelihood of breast cancer recurrence and chemotherapy responsiveness. The aims of this study were to describe temporal trends in assay usage, to investigate factors associated with the receipt of the assay and to determine how the assay is associated with treatment decisions. Random samples of stage I-II female breast cancer patients diagnosed in 2004, 2005 and 2010 as reported to the National Cancer Institute's Surveillance Epidemiology and End Results program were included. Among women diagnosed in 2010 with estrogen receptor positive (ER+), lymph node-negative (LN-) tumors, factors associated with receipt of the assay were identified and the likelihood of chemotherapy by RS was estimated. Assay usage increased over time (ER+/LN-:8.0-27.0 %, p < 0.01; ER+/LN+: 2.0-15.7 %, p = 0.09; ER-: 0.2-1.7 %, p < 0.01) from 2005 to 2010. Receipt of the assay was associated with younger age, lower area income and tumor characteristics. Among women in the low (RS < 18) and high risk (RS > 30) categories, 3.3 and 95.9 % received chemotherapy, respectively. Within the intermediate risk group the receipt of chemotherapy varied: 12.8 % (RS: 18-19), 35.0 % (RS: 20-23) and 84.0 % (RS: 24-30). During the study years, assay usage increased among women for whom the assay is and is not guideline recommended. Factors such as insurance and race/ethnicity do not appear to be associated with the receipt of the assay. The RS, as determined broadly via three categories and within the intermediate risk group, does appear to influence chemotherapy decisions.