Vision foundation models (VFM), pre-trained on large image datasets and capable of capturing rich feature representations, have recently shown potential for zero-shot image registration. However, their performance has mostly been tested in the context of less complex structures, such as the brain or abdominal organs, and it remains unclear whether these models can handle more challenging, deformable anatomy. Breast MRI registration is particularly challenging due to anatomical variation between patients, deformation from positioning, and the thin, complex structure of fibroglandular tissue (FGT), where accurate alignment is crucial. In this study, we provide a comprehensive evaluation of VFM-based registration algorithms.Gu, HanxueChen, YaqianKonz, NicholasLi, QihangMazurowski, Maciej A. We assess five pre-trained encoders, including DINO-v2, SAM, MedSAM, SSLSAM, and MedCLIP, across four key breast registration tasks that capture variations in different years and dates, sequences, modalities, and patient disease status (lesion versus no lesion). Our results show that among the five pre-trained encoders, SAM demonstrates a clear advantage. VFM outperforms traditional optimization-based methods, especially in cross-modality tasks, with its advantage more pronounced for large structures (e.g., organs and breast) than for finer anatomical details like FGT. Further work is needed to understand how domain-specific training influences registration and to explore targeted strategies that improve fine structure accuracy. We also publicly release our code at Github .