Breast cancer has become a significant health problem worldwide as it is considered one of the primary causes for deaths amongst females. In order to prevent the increase of deaths caused by breast cancer, early diagnosis through computer aided diagnosis systems has been very effective. This paper introduces a computer aided system for detecting and classifying suspicious regions in digital mammograms. The system starts by extracting regions of interest that are suspicious of containing cancerous cells. Then, all these regions are classified to check whether they are normal or abnormal. For the detection phase, template matching techniques are utilized. As for the classification phase, a 3-step process is applied which enclose feature extraction with wavelet transform, feature selection with statistical techniques and classification with clustering K-Nearest Neighbor classifier. A preliminary result shows a 97.73 accuracy rate. © 2014 IEEE.