In this work we explore sparsity-based approaches for the task of liver metastases detection in liver computed-tomography (CT) examinations. Sparse signal representation has proven to be a very powerful tool for robustly acquiring, representing, and compressing high-dimensional signals that can be accurately constructed from a compact, fixed set basis. We explore different sparsity based classification techniques and compare them to state of the art classification schemes. These methods were tested on CT examinations from 20 patients taken in different times, with overall 68 lesions. Best performance was achieved using the label consistent K-SVD (LC-KSVD) method, with detection rate of 91%, 0.9 false positive (FP) rate and classification accuracy (ACC) of 96%. The detection rates as well as the classification results are promising. Future work entails expanding the method to 3D analysis as well as testing it on a larger database.