Selecting proper clients to participate in the iterative federated learning (FL) rounds is critical to effectively harness a broad range of distributed datasets. Existing client selection methods simply consider the variability among FL clients with uni-modal data, however, have yet to consider clients with multi-modalities. We reveal that traditional client selection scheme in MFL may suffer from a severe modality-level bias, which impedes the collaborative exploitation of multi-modal data, leading to insufficient local data exploration and global aggregation. To tackle this challenge, we propose a Client-wise Modality Selection scheme for MFL (CMSFed) that can comprehensively utilize information from each modality via avoiding such client selection bias caused by modality imbalance. Specifically, in each MFL round, the local data from different modalities are selectively employed to participate in local training and aggregation to mitigate potential modality imbalance of the global model. To approximate the fully aggregated model update in a balanced way, we introduce a novel local training loss function to enhance the weak modality and align the divergent feature spaces caused by inconsistent modality adoption strategies for different clients simultaneously. Then, a modality-level gradient decoupling method is designed to derive respective submodular functions to maintain the gradient diversity during the selection progress and balance MFL according to local modality imbalance in each iteration. Our extensive experiments showcase the superiority of CMSFed over baselines and its effectiveness in multi-modal data exploitation.