Four schemes to detect masses in digitized mammograms based on textural information are demonstrated and compared. Enhancement and segmentation of the image is performed using hexagonal wavelets, steerable filters, and Laws texture energy maps. Hexagonal wavelets are used because spectral orientation is partitioned into three bands covering the frequency domain equally. The lifting scheme is used to construct these wavelets, because it can be extended to uneven sampling, is not susceptible to boundary conditions, and is computationally efficient. It is found that with Laws, the specific convolutional mask is not as important as the pre-enhancement used. Steered filter enhancement shows the best results, closely followed by adaptive histogram equalization, with wavelet enhancement performing the poorest. Oriented filters are used for enhancement and orientation detection. A set of filters are designed that can be efficiently steered along the dominant orientation of the image.