We present a fully automatic approach to quantitatively analyze filopodia-based migration of fluorescent cells in 3D time-lapse series. The proposed method involves three steps. First, each frame of the time-lapse series is preprocessed using a steerable filter and binarized to obtain a coarse segmentation of the cell shape. Second, a sequence of morphological filters is applied on the coarse binary mask to separate the cell body from individual filopodia. Finally, their length is estimated using a geodesic distance transform. The proposed approach is validated on 3D time-lapse series of lung adenocarcinoma cells. We show that the number of filopodia and their average length can be used as a descriptor to discriminate between different phenotypes of migrating cells.