Breast cancer is the leading cause of deaths among women. To reduce the number of deaths, early diagnosis and treatment have been pointed at as the most reliable approach. This paper introduces the application of cluster-knearest neighbor for breast cancer diagnosis. First, we apply wavelet transform to extract features. Feature selection is applied to select the most relevant features out of the huge number of coefficients that are extracted. After that, we apply the cluster-k-nearest neighbor classifier for classification. © 2012 American Institute of Physics.