unique values from a django model field containing CSVs

models.py

from django.db import models


class Record(models.Model):

    types = models.CharField(db_index=True)
    # ... some other stuff ...

    @classmethod
    def distinct_types(cls):
        """
        Return a list of unique types from all Records
        """
        # all_types is a list of tuples, possibly containing CSVs
        all_types = cls.objects.order_by().values_list('types').distinct()

        # convert each tuple to a list, and reduce them into a single set of unique values
        all_types = reduce(lambda x, y: list(x) + list(y), all_types)

        # split all members of the set on ',' and reduce the expanded lists back into a set,
        # filtering out NULLs along the way.
        return set(reduce(lambda x, y: x + y, [t.split(',') for t in all_types if t is not None]))

Is there a more efficient way to do this?